Share Email Print

Proceedings Paper

Learning shape from focus using multilayer neural networks
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In this paper, we describe a novel use of neural networks for extracting three-dimensional shape of the objects based on image focus. The conventional shape from focus methods are based on piece-wise constant, or piece-wise planar approximation of the focused image surface (FIS) of the object, so they fail to provide accurate shape estimation for objects with complex geometry. The proposed scheme is based on representation of three-dimensional shape of FIS in a window in terms of the neural network weights. The neural network is trained to learn the shape of the FIS that maximizes the focus measure. The SFF problem has thus been converted to an ordinary optimization problem in which a criterion function (focus measure) is to be optimized (maximized) with respect to the network weights. Gradient accent method has been used to optimize the focus measure over the three-dimensional FIS. Experiments were conducted on three different types of objects to compare the performance of the proposed algorithm with that of traditional SFF methods. Experimental results demonstrate that the method of SFF using neural networks provides more accurate depth estimates than those by the traditional methods.

Paper Details

Date Published: 23 September 1999
PDF: 10 pages
Proc. SPIE 3811, Vision Geometry VIII, (23 September 1999); doi: 10.1117/12.364112
Show Author Affiliations
Asif Muhammad, Kwangju Institute of Science and Technology (South Korea)
Tae-Sun Choi, Kwangju Institute of Science and Technology (South Korea)

Published in SPIE Proceedings Vol. 3811:
Vision Geometry VIII
Longin Jan Latecki; Robert A. Melter; David M. Mount; Angela Y. Wu, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?